ik_llama_opt/ggml
Kawrakow ada5cc1523 Fused norm (#1086)
* Adding fused_norm - same idea as fused_rms_norm

* Avoid computing the attention reduce op for cohere2

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-12-24 15:22:43 +01:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Fused norm (#1086) 2025-12-24 15:22:43 +01:00
src Fused norm (#1086) 2025-12-24 15:22:43 +01:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Graph parallel: the next generation (#1080) 2025-12-24 08:31:48 +01:00